{"id":"https://openalex.org/W4415427972","doi":"https://doi.org/10.3233/faia251348","title":"PoemTale Diffusion: Minimising Information Loss in Poem to Image Generation with Multi-Stage Prompt Refinement","display_name":"PoemTale Diffusion: Minimising Information Loss in Poem to Image Generation with Multi-Stage Prompt Refinement","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415427972","doi":"https://doi.org/10.3233/faia251348"},"language":null,"primary_location":{"id":"doi:10.3233/faia251348","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251348","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia251348","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113721494","display_name":"S. Selina Jamil","orcid":null},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sofia Jamil","raw_affiliation_strings":["Indian Institute of Technology Patna"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Patna","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086599038","display_name":"B. Subba Reddy","orcid":"https://orcid.org/0000-0002-8610-4753"},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Bollampalli Areen Reddy","raw_affiliation_strings":["Indian Institute of Technology Patna"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Patna","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101714489","display_name":"Raghvendra Kumar","orcid":"https://orcid.org/0000-0003-1311-7585"},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Raghvendra Kumar","raw_affiliation_strings":["Indian Institute of Technology Patna"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Patna","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060797340","display_name":"Sriparna Saha","orcid":"https://orcid.org/0000-0001-5458-9381"},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sriparna Saha","raw_affiliation_strings":["Indian Institute of Technology Patna"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Patna","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083954626","display_name":"Koustava Goswami","orcid":"https://orcid.org/0000-0002-0428-160X"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Koustava Goswami","raw_affiliation_strings":["Adobe Research"],"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037701886","display_name":"K. J. Joseph","orcid":"https://orcid.org/0000-0003-0369-2674"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph K J","raw_affiliation_strings":["Adobe Research"],"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5113721494"],"corresponding_institution_ids":["https://openalex.org/I132153292"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.78783383,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9327999949455261,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9327999949455261,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.8848000168800354},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.6367999911308289},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.6241000294685364},{"id":"https://openalex.org/keywords/poetry","display_name":"Poetry","score":0.5996999740600586},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5320000052452087},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.47690001130104065}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8848000168800354},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7630000114440918},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6367999911308289},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.6241000294685364},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.5996999740600586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.552299976348877},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5320000052452087},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.47690001130104065},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.42820000648498535},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.39890000224113464},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35530000925064087},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26080000400543213},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26019999384880066}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia251348","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251348","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia251348","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251348","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,10,20,153,211],"text-to-image":[3,95],"diffusion":[4,122],"models":[5,34,123],"have":[6],"achieved":[7],"remarkable":[8],"success":[9],"generating":[11],"realistic":[12],"and":[13,77,172,190,199],"diverse":[14],"visual":[15],"content.":[16],"A":[17],"critical":[18],"factor":[19],"this":[21,50],"process":[22],"is":[23,91],"the":[24,88,110,146,154,160,194,212],"model\u2019s":[25],"ability":[26],"to":[27,59,86,108,134,144,150,204],"accurately":[28],"interpret":[29],"textual":[30],"prompts.":[31],"However,":[32],"these":[33],"often":[35],"struggle":[36],"with":[37,129,207],"creative":[38,68],"expressions,":[39],"particularly":[40],"those":[41],"involving":[42],"complex,":[43],"abstract,":[44,76],"or":[45],"highly":[46],"descriptive":[47],"language.":[48],"In":[49],"work,":[51],"we":[52,118,158],"introduce":[53,159],"a":[54,64,99,130,177,201],"novel":[55,202],"training-free":[56],"approach":[57,84],"tailored":[58],"improve":[60],"image":[61],"generation":[62,206],"for":[63,182],"unique":[65],"form":[66],"of":[67,112,156,165,179,196],"language:":[69],"poetic":[70,94,113],"verse,":[71],"which":[72,139],"frequently":[73],"features":[74],"layered,":[75],"dual":[78],"meanings.":[79],"Our":[80],"proposed":[81],"PoemTale":[82],"Diffusion":[83],"aims":[85],"minimise":[87],"information":[89,209],"that":[90],"lost":[92],"during":[93],"conversion":[96],"by":[97,124],"integrating":[98],"multi":[100],"stage":[101],"prompt":[102],"refinement":[103],"loop":[104],"into":[105],"Language":[106],"Models":[107],"enhance":[109],"interpretability":[111],"texts.":[114],"To":[115],"support":[116],"this,":[117],"adapt":[119],"existing":[120],"state-of-the-art":[121],"modifying":[125],"their":[126],"self-attention":[127,132],"mechanisms":[128],"consistent":[131,137],"technique":[133],"generate":[135],"multiple":[136,170],"images,":[138],"are":[140],"then":[141],"collectively":[142],"used":[143],"convey":[145],"poem\u2019s":[147],"meaning.":[148],"Moreover,":[149],"encourage":[151],"research":[152],"field":[155],"poetry,":[157],"P4I":[161],"(PoemForImage)":[162],"dataset,":[163],"consisting":[164],"1,111":[166],"poems":[167],"sourced":[168],"from":[169,187],"online":[171],"offline":[173],"resources.":[174],"We":[175],"engaged":[176],"panel":[178],"poetry":[180],"experts":[181],"qualitative":[183],"assessments.":[184],"The":[185],"results":[186],"both":[188],"human":[189],"quantitative":[191],"evaluations":[192],"validate":[193],"efficacy":[195],"our":[197],"method":[198],"contribute":[200],"perspective":[203],"poem-to-image":[205],"enhanced":[208],"capture":[210],"generated":[213],"images.":[214]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}
